Scholarlink

<p>Cloud computing, renowned for its on-demand resource provisioning and reliability, offers virtualized and distributed resources. Despite its benefits, the challenge of load balancing arises due to the large-scale data handling involved. Efficient load balancing is crucial for optimal resource utilization, user satisfaction, and minimizing energy consumption. Existing approaches face limitations, such as a lack of flexibility and the inability to measure key parameters. This study suggests a solution to these problems via MoLb approach using PSO with Enhanced Self-Adaptive Learning (ESL-PSO). The system, called MoLb, achieves load balancing without virtual machine (VM) migration; efficiently transferring workloads to compatible VMs. MoLb incorporates a VM A multi-objective task scheduling (MOTS) system with a workload prediction subsystem MOTS efficiency model, leveraging ESL-PSO. This comprehensive approach ensures even load distribution across the cloud cluster, enhancing performance and optimization. The whole task’s completion time, resource expenses, and energy use of the findings demonstrate how well the suggested strategy performs when compared to different methods. Experimental findings demonstrate that the MoLb method currently takes % less completion time than state-of-the-art methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-objective load balancing based on enhanced self-adaptive learning PSO

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Richa Sharma,
  • Ritika Sharma

摘要

Cloud computing, renowned for its on-demand resource provisioning and reliability, offers virtualized and distributed resources. Despite its benefits, the challenge of load balancing arises due to the large-scale data handling involved. Efficient load balancing is crucial for optimal resource utilization, user satisfaction, and minimizing energy consumption. Existing approaches face limitations, such as a lack of flexibility and the inability to measure key parameters. This study suggests a solution to these problems via MoLb approach using PSO with Enhanced Self-Adaptive Learning (ESL-PSO). The system, called MoLb, achieves load balancing without virtual machine (VM) migration; efficiently transferring workloads to compatible VMs. MoLb incorporates a VM A multi-objective task scheduling (MOTS) system with a workload prediction subsystem MOTS efficiency model, leveraging ESL-PSO. This comprehensive approach ensures even load distribution across the cloud cluster, enhancing performance and optimization. The whole task’s completion time, resource expenses, and energy use of the findings demonstrate how well the suggested strategy performs when compared to different methods. Experimental findings demonstrate that the MoLb method currently takes % less completion time than state-of-the-art methods.